All flash array, how can bottleneck be Source?

Availability for the Always-On Enterprise

Re: All flash array, how can bottleneck be Source?

Veeam Logoby tsightler » Wed Sep 07, 2016 4:54 pm 3 people like this post

First of all, have you already read the FAQ? It explains the bottleneck stats and how they are calculated fairly well:

veeam-backup-replication-f2/read-this-first-frequently-asked-questions-v7-t17633-15.html#p95291

If you have read that and still have questions, we can dig deeper, but suffice it to say that, as I tried to explain above, in your case, I would fully expect the flash storage to be the bottleneck. In simple terms, as little as the source is being utilized, everything else in the chain is being utilized far less.

Now it's true that Veeam could probably push the storage harder and read data from the device more aggressively, and if we did so, it might move the bottleneck to the CPU, or even the target, but in your case the entire backup is taking only 13 minutes (minus the indexing which isn't part of the backup dataflow), so there's not a ton to be gained overall, perhaps a few minutes.
tsightler
Veeam Software
 
Posts: 4768
Liked: 1737 times
Joined: Fri Jun 05, 2009 12:57 pm
Full Name: Tom Sightler

Previous

Return to Veeam Backup & Replication



Who is online

Users browsing this forum: No registered users and 13 guests